spice-acceleration
Warn
Audited by Snyk on Apr 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly instructs bootstrapping/ingesting data from external sources—e.g., s3:// snapshots, external Postgres, Kafka/Debezium/DynamoDB streams and HTTP endpoints—so the agent will fetch and read untrusted third-party content as part of its workflow.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata